模型创建初步

模型创建初步

一 模型创建步骤

二 nn.Module属性

三 模型容器和AlexNet

一 create_module.py

 @brief      : 学习模型创建学习

import os
import random
import numpy as np
import torch
import torch.nn as nn
from torch.utils.data import DataLoader
import torchvision.transforms as transforms
import torch.optim as optim
from matplotlib import pyplot as plt
from model.lenet import LeNet
from tools.my_dataset import RMBDataset


def set_seed(seed=1):
    random.seed(seed)
    np.random.seed(seed)
    torch.manual_seed(seed)
    torch.cuda.manual_seed(seed)


set_seed()  # 设置随机种子
rmb_label = {"1": 0, "100": 1}

# 参数设置
MAX_EPOCH = 10
BATCH_SIZE = 16
LR = 0.01
log_interval = 10
val_interval = 1

# ============================ step 1/5 数据 ============================

split_dir = os.path.join("..", "..", "data", "rmb_split")
train_dir = os.path.join(split_dir, "train")
valid_dir = os.path.join(split_dir, "valid")

norm_mean = [0.485, 0.456, 0.406]
norm_std = [0.229, 0.224, 0.225]

train_transform = transforms.Compose([
    transforms.Resize((32, 32)),
    transforms.RandomCrop(32, padding=4),
    transforms.ToTensor(),
    transforms.Normalize(norm_mean, norm_std),
])

valid_transform = transforms.Compose([
    transforms.Resize((32, 32)),
    transforms.ToTensor(),
    transforms.Normalize(norm_mean, norm_std),
])

# 构建MyDataset实例
train_data = RMBDataset(data_dir=train_dir, transform=train_transform)
valid_data = RMBDataset(data_dir=valid_dir, transform=valid_transform)

# 构建DataLoder
train_loader = DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)
valid_loader = DataLoader(dataset=valid_data, batch_size=BATCH_SIZE)

# ============================ step 2/5 模型 ============================
net = LeNet(classes=2)
net.initialize_weights()

# ============================ step 3/5 损失函数 ============================
criterion = nn.CrossEntropyLoss()                                                   # 选择损失函数

# ============================ step 4/5 优化器 ============================
optimizer = optim.SGD(net.parameters(), lr=LR, momentum=0.9)                        # 选择优化器
scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=10, gamma=0.1)     # 设置学习率下降策略

# ============================ step 5/5 训练 ============================
train_curve = list()
valid_curve = list()

for epoch in range(MAX_EPOCH):

    loss_mean = 0.
    correct = 0.
    total = 0.

    net.train()
    for i, data in enumerate(train_loader):

        # forward
        inputs, labels = data
        outputs = net(inputs)

        # backward
        optimizer.zero_grad()
        loss = criterion(outputs, labels)
        loss.backward()

        # update weights
        optimizer.step()

        # 统计分类情况
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).squeeze().sum().numpy()

        # 打印训练信息
        loss_mean += loss.item()
        train_curve.append(loss.item())
        if (i+1) % log_interval == 0:
            loss_mean = loss_mean / log_interval
            print("Training:Epoch[{:0>3}/{:0>3}] Iteration[{:0>3}/{:0>3}] Loss: {:.4f} Acc:{:.2%}".format(
                epoch, MAX_EPOCH, i+1, len(train_loader), loss_mean, correct / total))
            loss_mean = 0.

    scheduler.step()  # 更新学习率

    # validate the model
    if (epoch+1) % val_interval == 0:

        correct_val = 0.
        total_val = 0.
        loss_val = 0.
        net.eval()
        with torch.no_grad():
            for j, data in enumerate(valid_loader):
                inputs, labels = data
                outputs = net(inputs)
                loss = criterion(outputs, labels)

                _, predicted = torch.max(outputs.data, 1)
                total_val += labels.size(0)
                correct_val += (predicted == labels).squeeze().sum().numpy()

                loss_val += loss.item()

            valid_curve.append(loss_val)
            print("Valid:\t Epoch[{:0>3}/{:0>3}] Iteration[{:0>3}/{:0>3}] Loss: {:.4f} Acc:{:.2%}".format(
                epoch, MAX_EPOCH, j+1, len(valid_loader), loss_val, correct / total))


train_x = range(len(train_curve))
train_y = train_curve

train_iters = len(train_loader)
valid_x = np.arange(1, len(valid_curve)+1) * train_iters*val_interval # 由于valid中记录的是epochloss，需要对记录点进行转换到iterations
valid_y = valid_curve

plt.plot(train_x, train_y, label='Train')
plt.plot(valid_x, valid_y, label='Valid')

plt.legend(loc='upper right')
plt.ylabel('loss value')
plt.xlabel('Iteration')
plt.show()

# ============================ inference ============================

BASE_DIR = os.path.dirname(os.path.abspath(__file__))
test_dir = os.path.join(BASE_DIR, "test_data")

test_data = RMBDataset(data_dir=test_dir, transform=valid_transform)
valid_loader = DataLoader(dataset=test_data, batch_size=1)

for i, data in enumerate(valid_loader):
    # forward
    inputs, labels = data
    outputs = net(inputs)
    _, predicted = torch.max(outputs.data, 1)

    rmb = 1 if predicted.numpy()[0] == 0 else 100
    print("模型获得{}元".format(rmb))

二 模型容器与AlexNet构建

一 module_containers.py

# @brief      : 模型容器——Sequential, ModuleList, ModuleDict
"""
import torch
import torchvision
import torch.nn as nn
from collections import OrderedDict


# ============================ Sequential
class LeNetSequential(nn.Module):
    def __init__(self, classes):
        super(LeNetSequential, self).__init__()
        self.features = nn.Sequential(
            nn.Conv2d(3, 6, 5),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2),
            nn.Conv2d(6, 16, 5),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2),)

        self.classifier = nn.Sequential(
            nn.Linear(16*5*5, 120),
            nn.ReLU(),
            nn.Linear(120, 84),
            nn.ReLU(),
            nn.Linear(84, classes),)

    def forward(self, x):
        x = self.features(x)
        x = x.view(x.size()[0], -1)
        x = self.classifier(x)
        return x


class LeNetSequentialOrderDict(nn.Module):
    def __init__(self, classes):
        super(LeNetSequentialOrderDict, self).__init__()

        self.features = nn.Sequential(OrderedDict({
            'conv1': nn.Conv2d(3, 6, 5),
            'relu1': nn.ReLU(inplace=True),
            'pool1': nn.MaxPool2d(kernel_size=2, stride=2),

            'conv2': nn.Conv2d(6, 16, 5),
            'relu2': nn.ReLU(inplace=True),
            'pool2': nn.MaxPool2d(kernel_size=2, stride=2),
        }))

        self.classifier = nn.Sequential(OrderedDict({
            'fc1': nn.Linear(16*5*5, 120),
            'relu3': nn.ReLU(),

            'fc2': nn.Linear(120, 84),
            'relu4': nn.ReLU(inplace=True),

            'fc3': nn.Linear(84, classes),
        }))

    def forward(self, x):
        x = self.features(x)
        x = x.view(x.size()[0], -1)
        x = self.classifier(x)
        return x


# net = LeNetSequential(classes=2)
# net = LeNetSequentialOrderDict(classes=2)
#
# fake_img = torch.randn((4, 3, 32, 32), dtype=torch.float32)
#
# output = net(fake_img)
#
# print(net)
# print(output)


# ============================ ModuleList

class ModuleList(nn.Module):
    def __init__(self):
        super(ModuleList, self).__init__()
        self.linears = nn.ModuleList([nn.Linear(10, 10) for i in range(20)])

    def forward(self, x):
        for i, linear in enumerate(self.linears):
            x = linear(x)
        return x


# net = ModuleList()
#
# print(net)
#
# fake_data = torch.ones((10, 10))
#
# output = net(fake_data)
#
# print(output)


# ============================ ModuleDict

class ModuleDict(nn.Module):
    def __init__(self):
        super(ModuleDict, self).__init__()
        self.choices = nn.ModuleDict({
            'conv': nn.Conv2d(10, 10, 3),
            'pool': nn.MaxPool2d(3)
        })

        self.activations = nn.ModuleDict({
            'relu': nn.ReLU(),
            'prelu': nn.PReLU()
        })

    def forward(self, x, choice, act):
        x = self.choices[choice](x)
        x = self.activations[act](x)
        return x


net = ModuleDict()

fake_img = torch.randn((4, 10, 32, 32))

output = net(fake_img, 'conv', 'relu')

print(output)




# 4 AlexNet

alexnet = torchvision.models.AlexNet()

三 nn网络层-卷积层

一 nn_layers_convolution.py

# @brief      : 学习卷积层

import os
import torch.nn as nn
from PIL import Image
from torchvision import transforms
from matplotlib import pyplot as plt
from tools.common_tools import transform_invert, set_seed

set_seed(3)  # 设置随机种子

# ================================= load img ==================================
path_img = os.path.join(os.path.dirname(os.path.abspath(__file__)), "lena.png")
img = Image.open(path_img).convert('RGB')  # 0~255

# convert to tensor
img_transform = transforms.Compose([transforms.ToTensor()])
img_tensor = img_transform(img)
img_tensor.unsqueeze_(dim=0)    # C*H*W to B*C*H*W

# ================================= create convolution layer ==================================

# ================ 2d
flag = 1
# flag = 0
if flag:
    conv_layer = nn.Conv2d(3, 1, 3)   # input:(i, o, size) weights:(o, i , h, w)
    nn.init.xavier_normal_(conv_layer.weight.data)

    # calculation
    img_conv = conv_layer(img_tensor)

# ================ transposed
# flag = 1
flag = 0
if flag:
    conv_layer = nn.ConvTranspose2d(3, 1, 3, stride=2)   # input:(i, o, size)
    nn.init.xavier_normal_(conv_layer.weight.data)

    # calculation
    img_conv = conv_layer(img_tensor)


# ================================= visualization ==================================
print("卷积前尺寸:{}\n卷积后尺寸:{}".format(img_tensor.shape, img_conv.shape))
img_conv = transform_invert(img_conv[0, 0:1, ...], img_transform)
img_raw = transform_invert(img_tensor.squeeze(), img_transform)
plt.subplot(122).imshow(img_conv, cmap='gray')
plt.subplot(121).imshow(img_raw)
plt.show()

二 common_tools.py

# @brief      : 通用函数



import torch
import random
import numpy as np
from PIL import Image
import torchvision.transforms as transforms


def transform_invert(img_, transform_train):
    """
    将data 进行反transfrom操作
    :param img_: tensor
    :param transform_train: torchvision.transforms
    :return: PIL image
    """
    if 'Normalize' in str(transform_train):
        norm_transform = list(filter(lambda x: isinstance(x, transforms.Normalize), transform_train.transforms))
        mean = torch.tensor(norm_transform[0].mean, dtype=img_.dtype, device=img_.device)
        std = torch.tensor(norm_transform[0].std, dtype=img_.dtype, device=img_.device)
        img_.mul_(std[:, None, None]).add_(mean[:, None, None])

    img_ = img_.transpose(0, 2).transpose(0, 1)  # C*H*W --> H*W*C
    if 'ToTensor' in str(transform_train):
        img_ = img_.detach().numpy() * 255

    if img_.shape[2] == 3:
        img_ = Image.fromarray(img_.astype('uint8')).convert('RGB')
    elif img_.shape[2] == 1:
        img_ = Image.fromarray(img_.astype('uint8').squeeze())
    else:
        raise Exception("Invalid img shape, expected 1 or 3 in axis 2, but got {}!".format(img_.shape[2]) )

    return img_


def set_seed(seed=1):
    random.seed(seed)
    np.random.seed(seed)
    torch.manual_seed(seed)
    torch.cuda.manual_seed(seed)

四 nn网络层-池化-线性-激活函数

一 nn_layers_others.py

# @brief      : 其它网络层
import os
import torch
import random
import numpy as np
import torchvision
import torch.nn as nn
from torchvision import transforms
from matplotlib import pyplot as plt
from PIL import Image
from tools.common_tools import transform_invert, set_seed

set_seed(1)  # 设置随机种子

# ================================= load img ==================================
path_img = os.path.join(os.path.dirname(os.path.abspath(__file__)), "lena.png")
img = Image.open(path_img).convert('RGB')  # 0~255

# convert to tensor
img_transform = transforms.Compose([transforms.ToTensor()])
img_tensor = img_transform(img)
img_tensor.unsqueeze_(dim=0)    # C*H*W to B*C*H*W

# ================================= create convolution layer ==================================

# ================ maxpool
# flag = 1
flag = 0
if flag:
    maxpool_layer = nn.MaxPool2d((2, 2), stride=(2, 2))   # input:(i, o, size) weights:(o, i , h, w)
    img_pool = maxpool_layer(img_tensor)

# ================ avgpool
# flag = 1
flag = 0
if flag:
    avgpoollayer = nn.AvgPool2d((2, 2), stride=(2, 2))   # input:(i, o, size) weights:(o, i , h, w)
    img_pool = avgpoollayer(img_tensor)

# ================ avgpool divisor_override
# flag = 1
flag = 0
if flag:
    img_tensor = torch.ones((1, 1, 4, 4))
    avgpool_layer = nn.AvgPool2d((2, 2), stride=(2, 2), divisor_override=3)
    img_pool = avgpool_layer(img_tensor)

    print("raw_img:\n{}\npooling_img:\n{}".format(img_tensor, img_pool))


# ================ max unpool
# flag = 1
flag = 0
if flag:
    # pooling
    img_tensor = torch.randint(high=5, size=(1, 1, 4, 4), dtype=torch.float)
    maxpool_layer = nn.MaxPool2d((2, 2), stride=(2, 2), return_indices=True)
    img_pool, indices = maxpool_layer(img_tensor)

    # unpooling
    img_reconstruct = torch.randn_like(img_pool, dtype=torch.float)
    maxunpool_layer = nn.MaxUnpool2d((2, 2), stride=(2, 2))
    img_unpool = maxunpool_layer(img_reconstruct, indices)

    print("raw_img:\n{}\nimg_pool:\n{}".format(img_tensor, img_pool))
    print("img_reconstruct:\n{}\nimg_unpool:\n{}".format(img_reconstruct, img_unpool))


# ================ linear
flag = 1
# flag = 0
if flag:
    inputs = torch.tensor([[1., 2, 3]])
    linear_layer = nn.Linear(3, 4)
    linear_layer.weight.data = torch.tensor([[1., 1., 1.],
                                             [2., 2., 2.],
                                             [3., 3., 3.],
                                             [4., 4., 4.]])

    linear_layer.bias.data.fill_(0.5)
    output = linear_layer(inputs)
    print(inputs, inputs.shape)
    print(linear_layer.weight.data, linear_layer.weight.data.shape)
    print(output, output.shape)


# ================================= visualization ==================================
# print("池化前尺寸:{}\n池化后尺寸:{}".format(img_tensor.shape, img_pool.shape))
# img_pool = transform_invert(img_pool[0, 0:3, ...], img_transform)
# img_raw = transform_invert(img_tensor.squeeze(), img_transform)
# plt.subplot(122).imshow(img_pool)
# plt.subplot(121).imshow(img_raw)
# plt.show()